Learn LLM Path / pillar 9 of 10
Free track: every swapped resource costs $0. Concepts you already checked stay checked.
stop guess-and-tweak. Evaluation-driven development is the single biggest predictor of agent-building success (per Andrew Ng)
- Sign in to track this item
Objective vs LLM-judge; error analysis; traces KEY
Agentic AI - Module 4 (Andrew Ng) ↗videoFREEin course
- Sign in to track this item
RAG evals (RAGAS): faithfulness, precision, recall
RAG Evaluation, RAGAS explained - Logical Lenses ↗videoFREE12m
- Sign in to track this item
RAGAS in code (run in CI)
RAGAS Evaluation Tutorial (local, no API) - write-up ↗articleFREEread
- Sign in to track this item
Tracing/observability in practice
LangSmith docs ↗docsFREEdocs
Free · Extras
- Sign in to track this item
Structured eval workflows, debugging
Evaluating and Debugging Generative AI - DeepLearning.AI (W&B)video~1h⚠ link unverified
- Sign in to track this item
Serving an LLM app behind an API
FastAPI official tutorial (streaming/SSE section)videofree docs⚠ link unverified
- Sign in to track this item
Containerizing AI apps
Docker official docs - multi-stage buildsdocsreuse existing skill⚠ link unverified
- Sign in to track this item
Vector DB hosting choices
Qdrant/Weaviate/pgvector - official quickstart docs (all have free tiers)docspick one, go deep⚠ link unverified
- Sign in to track this item
Cost & latency optimization
Provider docs on caching, batching, streaming (OpenAI/Anthropic docs)docsread⚠ link unverified
- Sign in to track this item
Rate limiting & retries
tenacity / backoff library docs (Python)docscode-along⚠ link unverified
- Sign in to track this item
CI/CD gating on evals
GitHub Actions docs + RAGAS-in-CI write-up (Phase 4c)repofree⚠ link unverified
- Sign in to track this item
Monitoring in production
LangSmith docs (free tier) or open-source alternative (e.g. Langfuse self-hosted, free)docsfree tier⚠ link unverified